A Multi-Relational Approach to Clustering Trajectory Data

We propose a novel methodology for clustering multi-relational trajectory data. Our methodology consists of two steps. Initially, tuple linkages, defined in the database schema of the multi-relational trajectories, are leveraged to virtually organize the available route data into as many transactions, i.e. as sets of feature-value pairs. The identified transactions are then partitioned into homogeneous groups. Each discovered cluster is equipped with a representative, that provides an explanation of the corresponding group of trajectories, in terms of those feature-value pairs that are most likely to appear in a transaction belonging to that particular group. Outliers trajectories are placed into a trash cluster, that is finally partitioned to mitigate the dissimilarity between the trash cluster and the previously generated clusters.